Compositional Image Generation

Overview

The field aims to make image generators reliably follow instructions about what belongs in a scene, where it goes, how objects relate, and which details come from reference images. Approaches include layout- and graph-conditioned diffusion, spatial and occlusion controls, modular adapters and layered synthesis, and agentic planning with iterative generation and editing. Evaluation spans layout-to-image, multi-subject and multi-reference tasks, with benchmarks such as CogCanvas and TRACE-Bench probing identity, attribute binding, relations, and spatial accuracy. A central challenge is generalizing to unfamiliar combinations and crowded scenes: binding and identity errors grow with complexity, while stronger control must preserve image quality and remain efficient.

Latest papers

95 papers8 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

Feb 3, 2026

REPA-G: Test-Time Conditioning with Representation-Aligned Visual Features

While representation alignment with self-supervised models has been shown to improve diffusion model training, its potential for enhancing inference-time conditioning remains largely unexplored. We introduce Representation-Aligned Guidance (REPA-G), a framework that leverages these aligned representations, with rich semantic properties, to enable test-time conditioning from features, in generation. By optimizing a similarity objective (the potential) at inference, we steer the denoising process toward a conditioned representation extracted from a pre-trained feature extractor. Our method provides versatile control at multiple levels of granularity, ranging from patch level matching via single patches to broad semantic guidance using global image feature tokens. We further extend this to multi-concept composition, allowing for the faithful combination of distinct concepts. REPA-G operates entirely at inference time with no additional training required, offering a flexible and precise alternative to often ambiguous text prompts or coarse class labels. Our approach achieves high-quality, diverse generations on ImageNet and COCO. Code is available at https://github.com/valeoai/REPA-G
Nov 27, 2025

Generative Anchored Fields: Endpoint Learning for Generative Modeling

We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors, JJ (noise) and KK (data), from any point on a linear bridge. Instead of learning the local path along a trajectory, as in diffusion or flow-based models, GAF is trained to identify the endpoint coordinates of a bridge state directly via an endpoint regression objective. Central to our approach is the decoupling of time-dependent feature learning from endpoint prediction. Unlike the transport-based models that learn a monolithic time-conditioned predictor that maps noise to data via a unified field, GAF uses a shared trunk, ΦΦ, which produces a time-conditioned feature bank and a pair of linear predictors, JJ and KK. This separation of feature learning from prediction enables Transport Algebra: algebraic operations on multiple JJ and KK heads for compositional sampling. Additionally, with class-specific KnK_n heads, where n∈{1,...,N}n\in\{1,...,N\} for NN classes, GAF defines directed transport maps between a shared base noise distribution and multiple data domains, allowing controllable interpolation, multi-class composition, and semantic editing. This is achieved either directly on the predicted data coordinates (KK) using (i) Iterative Endpoint Refinement (IER), a novel sampler that achieves high-quality generation in 5−85-8 forward steps, or (ii) on the derived velocity field v=K−Jv=K-J. GAF achieves strong sample quality with an FID of 2.25 on ImageNet 256×256256\times256 while treating compositional generation as an architectural primitive. Code available at https://github.com/IDLabMedia/GAF
Oct 23, 2025

CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas

Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group photo generation. Inspired by professional image-editing software, CanvasComposer allows users to place reference subjects on a shared canvas, where each subject keeps its own RGBA cutout of the input. This multi-reference canvas preserves reference content under overlap while providing an intuitive interface for organizing multiple identities; the subjects remain separate elements on the input canvas, and the model outputs a single personalized and harmonized image. To keep this representation efficient, transparent latent pruning retains only tokens from each subject's non-transparent region, and cross-reference training mitigates copy-paste artifacts by learning to harmonize references sampled from different images. Extensive experiments demonstrate that CanvasComposer achieves coherent generation and strong identity preservation compared to state-of-the-art methods in multi-human personalized image generation. Project page: https://snap-research.github.io/canvascomposer
Oct 3, 2025

What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectives

Compositional generalization, the ability to generate novel combinations of known concepts, is a key ingredient for visual generative models. Yet, not all mechanisms that enable or inhibit it are fully understood. In this work, we conduct a systematic study of which design choices critically determine compositional generalization in image and video generation. By isolating independent design axes, we identify two key factors strongly associated with compositional success: (i) whether the training objective operates on a discrete or continuous distribution, and (ii) the completeness of conditioning information about constituent factors during training. We also show that relaxing the discrete loss with an auxiliary continuous latent objective can partially recover compositional performance in discrete models like MaskGIT. Our findings, corroborated by diverse compositional tasks and preliminary evidence in world models and LLMs, motivate a shift toward continuous objectives for compositional generalization.
Mar 15, 2025

CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art

Text-to-Image (T2I) diffusion models have made rapid progress on semantic alignment (generating what is described in the prompt), yet users still lack reliable control over aesthetic composition (how visual elements are put together). Prior work often treats aesthetics as a single, preference-driven notion (e.g., "high quality", "detailed", "breathtaking"), which does not map cleanly to compositional intent. We propose Aesthetic Alignment: aligning generated images to explicit, user-specified compositional constraints. We operationalize these constraints using the Principles of Art (PoA)-e.g., Balance, Rhythm, and Emphasis-commonly used in art education to describe composition. To support this task, we introduce CompArt, a dataset of 80,032 WikiArt images augmented with captions and PoA analyses produced by a multimodal LLM under structured prompting. We further propose ArtDapter, a lightweight and disentangled adapter that enables steering a pretrained T2I model along 10 PoA dimensions while retaining the base model's semantic capability. Experiments on CompArt show improved adherence to PoA controls over strong baselines under a dual evaluation protocol.